首页> 外文期刊>IEEE Transactions on Image Processing >Siamese Regression Tracking With Reinforced Template Updating
【24h】

Siamese Regression Tracking With Reinforced Template Updating

机译:暹罗回归跟踪与强化模板更新

获取原文
获取原文并翻译 | 示例

摘要

Siamese networks are prevalent in visual tracking because of the efficient localization. The networks take both a search patch and a target template as inputs where the target template is usually from the initial frame. Meanwhile, Siamese trackers do not update network parameters online for real-time efficiency. The fixed target template and CNN parameters make Siamese trackers not effective to capture target appearance variations. In this paper, we propose a template updating method via reinforcement learning for Siamese regression trackers. We collect a series of templates and learn to maintain them based on an actor-critic framework. Among this framework, the actor network that is trained by deep reinforcement learning effectively updates the templates based on the tracking result on each frame. Besides the target template, we update the Siamese regression tracker online to adapt to target appearance variations. The experimental results on the standard benchmarks show the effectiveness of both template and network updating. The proposed tracker SiamRTU performs favorably against state-of-the-art approaches.
机译:由于有效的本地化,暹罗网络在视觉跟踪中普遍存在。该网络将搜索补丁和目标模板作为输入,其中目标模板通常来自初始帧。同时,暹罗跟踪器不会在线更新网络参数以进行实时效率。固定目标模板和CNN参数使暹罗跟踪器无效地捕获目标外观变化。在本文中,我们通过对暹罗回归跟踪器的加固学习提出模板更新方法。我们收集一系列模板,并学会根据演员 - 评论家框架来维护它们。在该框架中,由深增强学习训练的演员网络有效地基于每个帧上的跟踪结果更新模板。除了目标模板外,我们在线更新暹罗回归跟踪器,以适应目标外观变化。标准基准测试的实验结果显示了模板和网络更新的有效性。拟议的跟踪器SIAMRTU对最先进的方法进行了有利的方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号